scholarly journals From partial shape matching through local deformation to robust global shape similarity for object detection

CVPR 2011 ◽  
2011 ◽  
Author(s):  
Tianyang Ma ◽  
Longin Jan Latecki
Keyword(s):  
Object Detection ◽  
Shape Matching ◽  
Local Deformation ◽  
Shape Similarity ◽  
Global Shape ◽  
Partial Shape Matching

Object detection based on scale-invariant partial shape matching

2015 ◽  
Vol 26 (6) ◽  
pp. 711-721 ◽  
Author(s):  
Huijie Fan ◽  
Yang Cong ◽  
Yandong Tang
Keyword(s):  
Object Detection ◽  
Shape Matching ◽  
Scale Invariant ◽  
Partial Shape Matching

Fully Spectral Partial Shape Matching

2017 ◽  
Vol 36 (2) ◽  
pp. 247-258 ◽  
Author(s):  
O. Litany ◽  
E. Rodolà ◽  
A. M. Bronstein ◽  
M. M. Bronstein
Keyword(s):  
Shape Matching ◽  
Partial Shape Matching

A curvature salience descriptor for full and partial shape matching

2018 ◽  
Vol 77 (20) ◽  
pp. 27405-27426 ◽  
Author(s):  
Zhengbing Wang ◽  
Guili Xu ◽  
Yuehua Cheng ◽  
Ruipeng Guo ◽  
Zhengsheng Wang
Keyword(s):  
Shape Matching ◽  
Partial Shape Matching

scholarly journals Shape Similarity Measurement for Known-Object Localization: A New Normalized Assessment

2019 ◽  
Vol 5 (10) ◽  
pp. 77
Author(s):  
Baptiste Magnier ◽  
Behrang Moradi
Keyword(s):  
Shape Matching ◽  
Performance Measure ◽  
Object Localization ◽  
Similarity Measurement ◽  
Shape Similarity ◽  
Image Normalization ◽  
Object Shape ◽  
Binary Images ◽  
Candidate Image ◽  
Matching Estimation

This paper presents a new, normalized measure for assessing a contour-based object pose. Regarding binary images, the algorithm enables supervised assessment of known-object recognition and localization. A performance measure is computed to quantify differences between a reference edge map and a candidate image. Normalization is appropriate for interpreting the result of the pose assessment. Furthermore, the new measure is well motivated by highlighting the limitations of existing metrics to the main shape variations (translation, rotation, and scaling), by showing how the proposed measure is more robust to them. Indeed, this measure can determine to what extent an object shape differs from a desired position. In comparison with 6 other approaches, experiments performed on real images at different sizes/scales demonstrate the suitability of the new method for object-pose or shape-matching estimation.

scholarly journals 2D nonrigid partial shape matching using MCMC and contour subdivision

CVPR 2011 ◽  
2011 ◽  
Author(s):  
Yu Cao ◽  
Zhiqi Zhang ◽  
Irina Czogiel ◽  
Ian Dryden ◽  
Song Wang
Keyword(s):  
Shape Matching ◽  
Partial Shape Matching
Sign in / Sign up

Export Citation Format

Share Document